Application of adaptive neuro fuzzy inference system and genetic algorithm for pressure path optimization in sheet hydroforming process

Abstract

One of the most important parameters in success of sheet hydroforming process is loading (pressure) path. Improper pressure of fluid chamber during the process may cause a number of defects such as necking, tearing, and wrinkling. Theoretical calculations and finite element trial-and-error simulations to find the optimum pressure paths are so costly and time-consuming. This study underlines the application of adaptive neuro fuzzy inference system (ANFIS) and genetic algorithm (GA) for pressure path optimization in hydrodynamic hydroforming process of cylindrical-spherical parts. In this research, an ANFIS model has been developed based on finite element simulation results to identify the effect of the pressure path on the maximum thinning in the critical region of the part. In subsequent step, the ANFIS model operated as an objective function for optimization process. For this purpose, GA was incorporated into the ANFIS model to acquire the optimal pressure path in order to obtain minimum thinning in the critical region of the part. The results showed that the combination of adaptive neuro fuzzy inference approach and optimization algorithm is a good scheme to predict an improved loading pressure path minimizing the thinning in the critical region of the part and avoiding numerous trial and error simulations or experiments.